# Agent Master Data (remote · api.agentmasterdata.com)

Paid x402 API and MCP for trusted public master data, golden records, and reference data.

- Trust score: 78/100 (medium)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-06

## Components

- remote · `api.agentmasterdata.com`: 78/100 (this document), [markdown](https://verifymcp.io/servers/com-agentmasterdata-agent-master-data/api.md), [page](https://verifymcp.io/servers/com-agentmasterdata-agent-master-data/api)

## Channel facts

- Endpoint: `https://api.agentmasterdata.com/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `0.1.0`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-11-06.

- **Endpoint Security**: 83/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - No authorisation is required to call this server. Nothing on it is marked destructive, but we can't show that an anonymous caller can only read: full credit needs the server to list at least one tool and every tool to be verifiably read-only. We use a best-effort check of tool names and descriptions to tell read-only tools from tools that change things, so some genuinely read-only tools may not get full credit. Names that start with a read verb (get, list, read, search and similar) and accurate readOnlyHint annotations help. Meet that to earn full credit, or require authorisation.
  - HTTPS is enforced; there's no plaintext access path.
  - The HSTS (Strict-Transport-Security) header is present.
  - DNSSEC is configured correctly; the domain's records validate against the full chain to the root.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 78/100
  - 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 1384 tokens (~138/item across 10 items; 7 tools + 3 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 20/100
  - Stability observed for 6 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 95/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 86% of tool parameters carry a description.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 7 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 9 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a current MCP spec version (2026-07-28).

## Install

### How do I install the Agent Master Data MCP server?

Agent Master Data is a hosted endpoint at https://api.agentmasterdata.com/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add --transport http com-agentmasterdata-agent-master-data 'https://api.agentmasterdata.com/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "com-agentmasterdata-agent-master-data": {
      "url": "https://api.agentmasterdata.com/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "com-agentmasterdata-agent-master-data": {
      "type": "http",
      "url": "https://api.agentmasterdata.com/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.com-agentmasterdata-agent-master-data]
url = "https://api.agentmasterdata.com/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "com-agentmasterdata-agent-master-data": {
      "type": "remote",
      "url": "https://api.agentmasterdata.com/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add com-agentmasterdata-agent-master-data --url 'https://api.agentmasterdata.com/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  com-agentmasterdata-agent-master-data:
    url: "https://api.agentmasterdata.com/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "com-agentmasterdata-agent-master-data": {
      "Transport": "http",
      "Url": "https://api.agentmasterdata.com/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add com-agentmasterdata-agent-master-data -t streamable-http -u 'https://api.agentmasterdata.com/mcp'
```

### Other

```json
{
  "mcpServers": {
    "com-agentmasterdata-agent-master-data": {
      "type": "http",
      "url": "https://api.agentmasterdata.com/mcp"
    }
  }
}
```

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-11-06 (score 78, +1)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-11-04 (score 77, +1)

No change was recorded against any check on this day. Stability & Change Management went from 10 to 13. That category is still filling its 30-day observation window: 3 days of observed history at the previous scan, 4 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-02 (score 76, +1)

No change was recorded against any check on this day. Stability & Change Management went from 3 to 7. That category is still filling its 30-day observation window: 1 days of observed history at the previous scan, 2 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-01 (score 75, 0)

- [functional improvement] Stability: unverified → 0.03
- [cosmetic] Tool “search_master_data” changed its title: Search Trusted Master Data → Search Agent Master Data

### 2026-10-31 (score 75)

First indexed and scored.

## MCP tools (7)

### `get_master_data_schema` (~144 tokens)

Get Master Data Schema

Free discovery tool. Get supported public master-data entity types, identifiers, searchable attributes, relationships, reference domains, coverage, and freshness. Use this first when an agent does not know the data model or valid filters.

Input parameters:

- `entity_type`: Describe only this entity domain. Omitted means all v1 entity domains.
- `include_attributes` (boolean): When false, the attributes member is omitted from each described entity type.
- `include_identifiers` (boolean): When false, the identifiers member is omitted from each described entity type. primary_identifier is always present.
- `include_relationships` (boolean): When false, the relationships member is omitted from each described entity type.

### `search_master_data` (~135 tokens)

Search Agent Master Data

Paid x402 tool. Search trusted public master data for suppliers, locations, or organizations. Returns bounded golden-record summaries with match reasons, confidence, provenance, public-use status, freshness, and data-quality scores. Price ID: price.search.v1. Read masterdata://pricing before payment.

Input parameters:

- `cursor` (string): Opaque pagination cursor from a previous response's meta.next_cursor.
- `entity_type`: Restrict the search to one entity domain. Omitted means all v1 entity domains.
- `limit` (integer): Maximum number of results per page.
- `query` (string, required): Free-text search over golden records.

### `resolve_master_data_entity` (~99 tokens)

Resolve Master Data Entity

Paid x402 tool. Match incomplete or conflicting public supplier, location, or organization attributes to trusted master-data candidates. Returns explainable match evidence and never silently chooses an ambiguous entity. Price ID: price.resolve.v1.

Input parameters:

- `attributes` (object): Identifying attribute values keyed by field name, e.g. a name or an address line.
- `entity_type` (required)
- `identifiers` (array): Known identifiers of the entity being resolved.

### `get_master_data_golden_record` (~80 tokens)

Get Master Data Golden Record

Paid x402 tool. Retrieve one authoritative public golden record by stable record ID. Returns public attributes, identifiers, source-record lineage, survivorship evidence, freshness, relationships summary, and data quality. Price ID: price.record.v1.

Input parameters:

- `entity_type` (required)
- `record_id` (string, required): Golden-record identifier within the entity domain.

### `get_master_data_relationships` (~124 tokens)

Get Master Data Relationships

Paid x402 tool. Get governed public relationships for one master-data golden record, such as supplier ownership, location hierarchy, or organization parentage. Returns direction, validity dates, provenance, and confidence. Price IDs by requested depth: price.relationships.depth-1.v1, price.relationships.depth-2.v1, or price.relationships.depth-3.v1.

Input parameters:

- `depth` (integer): Traversal depth. Each depth is a separately priced tier.
- `entity_type` (required)
- `record_id` (string, required): Golden-record identifier within the entity domain.

### `get_reference_data` (~419 tokens)

Get Reference Data

Paid x402 tool. Get governed public reference data and controlled vocabulary values such as country, currency, unit of measure, industry, status, category, or code mappings. Returns codes, labels, definitions, validity dates, mappings, provenance, and version. Price ID: price.reference.v1.

Input parameters:

- `codes` (array): Exact codes wanted. Set membership, never a substring match; omit it to narrow nothing.
- `cursor` (string): Opaque continuation cursor from a prior identical request. Bound to the operation, the normalized request, and the data_version it paged.
- `domain` (string, required): Reference-data domain identifier, as get_master_data_schema names it.
- `include_inactive` (boolean): Whether values not KNOWN to be active at valid_at are served. False excludes them; true serves them flagged - active: false for a value declared inactive, beside the reference_value_inactive warning,…
- `limit` (integer): Page size, applied after query, codes, and validity have narrowed the list.
- `locale` (string): Language tag echoed on every served value and in the answer. Labels are served exactly as the snapshot stores them; there is no translation layer.
- `query` (string): Optional code or label search: a case-insensitive substring match against a value's code OR its label. Omit it to match every value.
- `valid_at` (string): The instant to evaluate each value's validity interval at. Defaults to the request clock. A value whose source DECLARES its interval is active when valid_from <= valid_at < valid_to, an absent or nul…

### `assess_master_data_quality` (~197 tokens)

Assess Master Data Quality

Paid x402 tool. Assess the completeness, validity, consistency, uniqueness, and freshness of a master-data record or supplied attributes. Returns explainable issues, severity, affected fields, policy rules, and safe remediation guidance without changing data. Price ID: price.quality.v1.

Input parameters:

- `attributes` (object): Candidate attributes to assess without writing them. Supply this or record_id, never both. No value submitted here is stored, published, or echoed: the answer names the input by its digest alone.
- `dimensions` (array): The quality dimensions to assess. A registered rule scoring a dimension not asked for is absent from the answer's issues, passed_rules, and not_evaluated_rules alike.
- `entity_type` (required)
- `include_remediation_guidance` (boolean): Whether each reported issue carries remediation guidance.
- `record_id` (string): Existing golden-record ID to assess. Supply this or attributes, never both.

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/com-agentmasterdata-agent-master-data/api#diagnostics

## Score history

- 2026-11-06: 78
- 2026-11-05: 77
- 2026-11-04: 77
- 2026-11-03: 76
- 2026-11-02: 76
- 2026-11-01: 75
- 2026-10-31: 75

## Common questions

### What is the Agent Master Data MCP server?

Agent Master Data is an MCP server listed in the public MCP registry as com.agentmasterdata/agent-master-data. Paid x402 API and MCP for trusted public master data, golden records, and reference data. This page covers its hosted endpoint (https://api.agentmasterdata.com/mcp).

### Is the Agent Master Data MCP server safe to use?

Agent Master Data scores 78 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the Agent Master Data MCP server expose?

Agent Master Data exposes 7 tools: get_master_data_schema, search_master_data, resolve_master_data_entity, get_master_data_golden_record, get_master_data_relationships, and 2 more. Their descriptions and schemas cost roughly 1,198 tokens of context every time the server is loaded.

### Does the Agent Master Data MCP server require authentication?

No. We connected to Agent Master Data without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

### Is the Agent Master Data MCP server still maintained?

Agent Master Data is still listed as active in the MCP registry. We last reached this channel on 6 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

### What did VerifyMCP test on the Agent Master Data MCP server?

VerifyMCP ran 13 checks on Agent Master Data, covering TLS certificate, Authorization, HTTPS, HSTS header and 9 more. Supply Chain Security and Provenance & Transparency do not apply to a hosted endpoint, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.

## Links

- Remote endpoint: https://api.agentmasterdata.com/mcp
- Changelog RSS feed: https://verifymcp.io/servers/com-agentmasterdata-agent-master-data/api.xml
- Changelog JSON feed: https://verifymcp.io/servers/com-agentmasterdata-agent-master-data/api/changelog.json
- Trust report (JSON): https://verifymcp.io/servers/com-agentmasterdata-agent-master-data/api.json
- HTML version of this page: https://verifymcp.io/servers/com-agentmasterdata-agent-master-data/api